Efficient encoding of video descriptor distribution for action recognition.
Mehrin SaremiFarzin YaghmaeePublished in: Multim. Tools Appl. (2020)
Keyphrases
- action recognition
- human actions
- action classification
- action detection
- spatial temporal
- video dataset
- recognition of human actions
- spatio temporal interest points
- computer vision
- bag of words
- activity recognition
- recognizing human actions
- static images
- space time interest points
- human detection
- motion features
- human activities
- recognizing actions
- body parts
- mid level
- bag of features
- video streams
- video sequences
- machine learning
- video content
- multimedia
- motion history images
- video data
- view invariant
- human pose
- key frames
- depth sensors
- object detection
- pose estimation
- action recognition in videos